{
  "_meta": {
    "source": "https://apipriceindex.com/api/openai/gpt-6-astra",
    "attribution": "apipriceindex.com",
    "license": "CC BY 4.0",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "note": "Free to reuse with attribution to apipriceindex.com.",
    "generated_at": "2026-09-05T08:15:05.915Z"
  },
  "id": "openai:gpt-6-astra",
  "name": "GPT-6 Astra (OpenAI)",
  "base_model": "gpt-6-astra",
  "provider": {
    "id": "openai",
    "name": "OpenAI",
    "url": "https://openai.com"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "vision",
    "function-calling"
  ],
  "context_window": 1000000,
  "max_output": 128000,
  "pricing": {
    "model_id": "openai:gpt-6-astra",
    "input": 10,
    "output": 50,
    "cached_input": null,
    "source_url": "https://openai.com/index/gpt-6-astra/",
    "verified_at": "2026-09-04T21:00:00Z",
    "sources": [
      {
        "name": "Provider page",
        "input": 10,
        "output": 50,
        "url": "https://openai.com/index/gpt-6-astra/",
        "verified_at": "2026-09-04T21:00:00Z"
      },
      {
        "name": "LiteLLM",
        "input": 10,
        "output": 50,
        "url": "https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json",
        "verified_at": "2026-09-03T20:47:46Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [],
  "latency": [],
  "license": null,
  "cutoff": {
    "cutoff": "2026-04",
    "label": "April 2026",
    "source_url": "https://platform.openai.com/docs/models"
  },
  "intelligence": null,
  "quality": null,
  "api": null,
  "facts": [
    "GPT-6 Astra (OpenAI) costs $10.00 input / $50.00 output per 1M tokens.",
    "A chatbot workload (1000 in / 500 out tokens) costs $35.00 per 1,000 requests.",
    "Cross-checked: LiteLLM's public price index independently lists OpenAI's gpt-6-astra at $10.00/$50.00 per 1M — corroborating the price shown here (within 0%).",
    "Handles a 1,000,000-token context window, up to 128,000 output tokens.",
    "Training knowledge cutoff: April 2026."
  ]
}